view contrib/plan9/9diff @ 40672:557d3509da55

tests: make test-alias.t pass with re2

Locally, these "non-ASCII character in alias" errors don't show up,
though I get them when the alias is defined at the command line rather
than in an hgrc.
The brokenness comes from the fact that hgrcs are parsed with regexes,
and re/re2 differ in this way:

$ python -c 'import re; print(re.compile("(.*)").match("aaa\xc0bbbb").groups())'
('aaa\xc0bbbb',)
$ python -c 'import re2; print(re2.compile("(.*)").match("aaa\xc0bbbb").groups())'
('aaa',)

Apparently re2 stops when it encounters invalid utf8 (which I suppose makes sense
given that '.' matches what appears to be a codepoint rather than a byte). This is
presumably a bug in hg, but not very important, so just change the test to stick
to valid utf8.

Differential Revision: https://phab.mercurial-scm.org/D5288

#!/bin/rc
# 9diff - Mercurial extdiff wrapper for diff(1)

rfork e

fn getfiles {
	cd $1 &&
	for(f in `{du -as | awk '{print $2}'})
		test -f $f && echo `{cleanname $f}
}

fn usage {
	echo >[1=2] usage: 9diff [diff options] parent child root
	exit usage
}

opts=()
while(~ $1 -*){
	opts=($opts $1)
	shift
}
if(! ~ $#* 3)
	usage

# extdiff will set the parent and child to a single file if there is
# only one change. If there are multiple changes, directories will be
# set. diff(1) does not cope particularly with directories; instead we
# do the recursion ourselves and diff each file individually.
if(test -f $1)
	diff $opts $1 $2
if not{
	# extdiff will create a snapshot of the working copy to prevent
	# conflicts during the diff. We circumvent this behavior by
	# diffing against the repository root to produce plumbable
	# output. This is antisocial.
	for(f in `{sort -u <{getfiles $1} <{getfiles $2}}){
		file1=$1/$f; test -f $file1 || file1=/dev/null
		file2=$3/$f; test -f $file2 || file2=/dev/null
		diff $opts $file1 $file2
	}
}
exit ''